© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178773
    Prev
    Next
    INDEX
    Explanations

    punctuation or word followed by related word

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign words, phrases, or non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vuttam
    0.48
    䊂
    0.43
     किम
    0.42
    靑
    0.42
    時
    0.41
     sabbam
    0.41
     तेज
    0.41
     Pank
    0.41
    㖦
    0.40
     時
    0.39
    POSITIVE LOGITS
    وی
    0.54
    궐
    0.52
     quanto
    0.52
    ட்
    0.52
    jà
    0.50
    স্ম
    0.49
     reread
    0.48
    dev
    0.48
    <h3>
    0.48
    ك
    0.47
    Activations Density 0.000%

    No Known Activations